Adaptive neuro-fuzzy controller for improved performance of a permanent magnet brushless DC motor

This paper deals with the mathematical modelling of a permanent magnet brushless DC motor, considering the nonlinearities in the torque-balance equation under a closed loop operation with a set reference speed. A controller based on the adaptive neuro-fuzzy inference system (ANFIS) is developed to minimize the overshoot and settling time following sudden changes in load torque. The entire system is modeled and simulated using the SIMULINK toolbox. The advantages of fuzzy logic and neural network are fused together to form a connectionist adaptive network based fuzzy logic controller. The required data for training the ANFIS controller are generated by simulation of the closed loop system with a conventional PID controller. The overshoot present in the transient response with conventional controller is eliminated using the ANFIS controller. The transient deviation of the response from the set reference following the variation in load torque is found to be negligibly small along with a desirable reduction in settling time for the ANFIS controller